Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Asja Fischer

Copula-Based Normalizing Flows


Jul 15, 2021
Mike Laszkiewicz, Johannes Lederer, Asja Fischer

* Accepted for presentation at the ICML 2021 Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+ 2021) 

  Access Paper or Ask Questions

A Novel Regression Loss for Non-Parametric Uncertainty Optimization


Jan 07, 2021
Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel

* Accepted at the 3rd Symposium on Advances in Approximate Bayesian Inference (AABI), code is available on: https://github.com/fraunhofer-iais/second-moment-loss. arXiv admin note: substantial text overlap with arXiv:2012.12687 

  Access Paper or Ask Questions

Second-Moment Loss: A Novel Regression Objective for Improved Uncertainties


Dec 23, 2020
Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel

* Code is available on: https://github.com/fraunhofer-iais/second-moment-loss 

  Access Paper or Ask Questions

Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification


Aug 17, 2020
Sina Däubener, Asja Fischer


  Access Paper or Ask Questions

Improving the Long-Range Performance of Gated Graph Neural Networks


Jul 19, 2020
Denis Lukovnikov, Jens Lehmann, Asja Fischer


  Access Paper or Ask Questions

Characteristics of Monte Carlo Dropout in Wide Neural Networks


Jul 10, 2020
Joachim Sicking, Maram Akila, Tim Wirtz, Sebastian Houben, Asja Fischer

* Accepted at the ICML 2020 workshop for Uncertainty and Robustness in Deep Learning 

  Access Paper or Ask Questions

On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions


Jun 26, 2020
Kai BrĂĽgge, Asja Fischer, Christian Igel


  Access Paper or Ask Questions

Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework


Jun 23, 2020
Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Mikhail Galkin, Sahand Sharifzadeh, Asja Fischer, Volker Tresp, Jens Lehmann


  Access Paper or Ask Questions

Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification


May 24, 2020
Sina Däubener, Lea Schönherr, Asja Fischer, Dorothea Kolossa


  Access Paper or Ask Questions

Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency


May 19, 2020
Mohammad Asif Khan, Fabien Cardinaux, Stefan Uhlich, Marc Ferras, Asja Fischer


  Access Paper or Ask Questions

Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery


May 01, 2020
Mike Laszkiewicz, Asja Fischer, Johannes Lederer

* 26 pages, 10 figures, 9 tables 

  Access Paper or Ask Questions

Leveraging Frequency Analysis for Deep Fake Image Recognition


Mar 20, 2020
Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, Thorsten Holz

* For accompanying code see https://github.com/RUB-SysSec/GANDCTAnalysis. 13 pages, 7 figures 

  Access Paper or Ask Questions

End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings


Feb 25, 2020
Rostislav Nedelchev, Debanjan Chaudhuri, Jens Lehmann, Asja Fischer


  Access Paper or Ask Questions

Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs


Jul 22, 2019
Nilesh Chakraborty, Denis Lukovnikov, Gaurav Maheshwari, Priyansh Trivedi, Jens Lehmann, Asja Fischer

* Preprint, under review. The first four authors contributed equally to this paper, and should be regarded as co-first authors 

  Access Paper or Ask Questions

Predictive Uncertainty Quantification with Compound Density Networks


Feb 04, 2019
Agustinus Kristiadi, Asja Fischer


  Access Paper or Ask Questions

Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters


Nov 13, 2018
Denis Lukovnikov, Nilesh Chakraborty, Jens Lehmann, Asja Fischer


  Access Paper or Ask Questions

Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge


Nov 05, 2018
Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann, Asja Fischer

* Published as conference paper at CoNLL 2018 

  Access Paper or Ask Questions

Learning to Rank Query Graphs for Complex Question Answering over Knowledge Graphs


Nov 02, 2018
Gaurav Maheshwari, Priyansh Trivedi, Denis Lukovnikov, Nilesh Chakraborty, Asja Fischer, Jens Lehmann


  Access Paper or Ask Questions

Three Factors Influencing Minima in SGD


Sep 13, 2018
Stanisław Jastrzębski, Zachary Kenton, Devansh Arpit, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

* First two authors contributed equally. Short version accepted into ICLR workshop. Accepted to Artificial Neural Networks and Machine Learning, ICANN 2018 

  Access Paper or Ask Questions

DNN's Sharpest Directions Along the SGD Trajectory


Jul 13, 2018
Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey

* Short version accepted into Modern Trends in Nonconvex Optimization for Machine Learning workshop at International Conference on Machine Learning 2018 

  Access Paper or Ask Questions

Incorporating Literals into Knowledge Graph Embeddings


May 25, 2018
Agustinus Kristiadi, Mohammad Asif Khan, Denis Lukovnikov, Jens Lehmann, Asja Fischer

* 9 pages, 2 figures, 6 tables 

  Access Paper or Ask Questions

On the regularization of Wasserstein GANs


Mar 05, 2018
Henning Petzka, Asja Fischer, Denis Lukovnicov

* Published as a conference paper at ICLR 2018. * Henning Petzka and Asja Fischer contributed equally to this work (11 pages +13 pages appendix) 

  Access Paper or Ask Questions

A Closer Look at Memorization in Deep Networks


Jul 01, 2017
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, Simon Lacoste-Julien

* Appears in Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Devansh Arpit, Stanis{\l}aw Jastrz\k{e}bski, Nicolas Ballas, and David Krueger contributed equally to this work 

  Access Paper or Ask Questions

Population-Contrastive-Divergence: Does Consistency help with RBM training?


Jun 28, 2017
Oswin Krause, Asja Fischer, Christian Igel

* An updated version is under review 

  Access Paper or Ask Questions

Graph-based Predictable Feature Analysis


May 11, 2017
Björn Weghenkel, Asja Fischer, Laurenz Wiskott


  Access Paper or Ask Questions

Bidirectional Helmholtz Machines


May 25, 2016
Jorg Bornschein, Samira Shabanian, Asja Fischer, Yoshua Bengio


  Access Paper or Ask Questions

STDP as presynaptic activity times rate of change of postsynaptic activity


Mar 21, 2016
Yoshua Bengio, Thomas Mesnard, Asja Fischer, Saizheng Zhang, Yuhuai Wu


  Access Paper or Ask Questions

Early Inference in Energy-Based Models Approximates Back-Propagation


Feb 07, 2016
Yoshua Bengio, Asja Fischer

* arXiv admin note: text overlap with arXiv:1509.05936 

  Access Paper or Ask Questions